Proceedings of the twenty-first international conference on Machine learning最新文献_第7页

SVM-based generalized multiple-instance learning via approximate box counting 基于svm的近似盒计数广义多实例学习

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015405

Qingping Tao, S. Scott, N. V. Vinodchandran, T. T. Osugi

引用次数: 100

Decision trees with minimal costs 成本最小的决策树

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015369

C. Ling, Qiang Yang, Jianning Wang, Shichao Zhang

引用次数: 306

P3VI: a partitioned, prioritized, parallel value iterator P3VI:分区、优先级、并行值迭代器

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015440

D. Wingate, Kevin Seppi

引用次数: 24

Learning to learn with the informative vector machine 学习用信息向量机学习

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015382

Neil D. Lawrence, John C. Platt

引用次数: 375

Testing the significance of attribute interactions 测试属性交互的重要性

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015377

Aleks Jakulin, I. Bratko

{"title":"Testing the significance of attribute interactions","authors":"Aleks Jakulin, I. Bratko","doi":"10.1145/1015330.1015377","DOIUrl":"https://doi.org/10.1145/1015330.1015377","url":null,"abstract":"Attribute interactions are the irreducible dependencies between attributes. Interactions underlie feature relevance and selection, the structure of joint probability and classification models: if and only if the attributes interact, they should be connected. While the issue of 2-way interactions, especially of those between an attribute and the label, has already been addressed, we introduce an operational definition of a generalized n-way interaction by highlighting two models: the reductionistic part-to-whole approximation, where the model of the whole is reconstructed from models of the parts, and the holistic reference model, where the whole is modelled directly. An interaction is deemed significant if these two models are significantly different. In this paper, we propose the Kirkwood superposition approximation for constructing part-to-whole approximations. To model data, we do not assume a particular structure of interactions, but instead construct the model by testing for the presence of interactions. The resulting map of significant interactions is a graphical model learned from the data. We confirm that the P-values computed with the assumption of the asymptotic X2 distribution closely match those obtained with the boot-strap.","PeriodicalId":159792,"journal":{"name":"Proceedings of the twenty-first international conference on Machine learning","volume":"965 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123070394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 150

Decentralized detection and classification using kernel methods 使用核方法的分散检测和分类

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015438

X. Nguyen, M. Wainwright, Michael I. Jordan

引用次数: 17

C4.5 competence map: a phase transition-inspired approach C4.5能力图:一种受阶段转变启发的方法

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015398

Nicolas Baskiotis, M. Sebag

引用次数: 14

Feature selection, L1 vs. L2 regularization, and rotational invariance 特征选择，L1与L2正则化和旋转不变性

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015435

A. Ng

引用次数: 1809

Utile distinction hidden Markov models 无差别隐马尔可夫模型

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015346

Daan Wierstra, M. Wiering

引用次数: 24

Text categorization with many redundant features: using aggressive feature selection to make SVMs competitive with C4.5 具有许多冗余特征的文本分类:使用积极的特征选择使svm与C4.5竞争

Proceedings of the twenty-first international conference on Machine learning Pub Date : 2004-07-04 DOI: 10.1145/1015330.1015388

E. Gabrilovich, Shaul Markovitch

引用次数: 246